English
Related papers

Related papers: Learning Stochastic Optimal Policies via Gradient …

200 papers

Stochastic gradient algorithms have been the main focus of large-scale learning problems and they led to important successes in machine learning. The convergence of SGD depends on the careful choice of learning rate and the amount of the…

Machine Learning · Computer Science 2015-11-03 Caglar Gulcehre , Marcin Moczulski , Yoshua Bengio

This paper investigates asymptotic behaviors of gradient descent algorithms (particularly accelerated gradient descent and stochastic gradient descent) in the context of stochastic optimization arising in statistics and machine learning…

Machine Learning · Statistics 2019-11-13 Yazhen Wang

The goal of policy gradient approaches is to find a policy in a given class of policies which maximizes the expected return. Given a differentiable model of the policy, we want to apply a gradient-ascent technique to reach a local optimum.…

Machine Learning · Computer Science 2019-11-13 Mattis Manfred Kämmerer

Trajectory optimization is a fundamental stochastic optimal control problem. This paper deals with a trajectory optimization approach for dynamical systems subject to measurement noise that can be fitted into linear time-varying stochastic…

Systems and Control · Electrical Eng. & Systems 2021-08-24 Prakash Mallick , Zhiyong Chen

We propose a novel approach to solving input- and state-constrained parametric mixed-integer optimal control problems using Differentiable Predictive Control (DPC). Our approach follows the differentiable programming paradigm by learning an…

Systems and Control · Electrical Eng. & Systems 2025-06-25 Ján Boldocký , Shahriar Dadras Javan , Martin Gulan , Martin Mönnigmann , Ján Drgoňa

There introduce Particle Optimized Gradient Descent (POGD), an algorithm based on the gradient descent but integrates the particle swarm optimization (PSO) principle to achieve the iteration. From the experiments, this algorithm has…

Machine Learning · Computer Science 2022-10-20 Feihu Han , Sida Xing , Sui Yang Khoo

Policy gradients methods apply to complex, poorly understood, control problems by performing stochastic gradient descent over a parameterized class of polices. Unfortunately, even for simple control problems solvable by standard dynamic…

Machine Learning · Computer Science 2022-06-22 Jalaj Bhandari , Daniel Russo

Increasing effort is put into the development of methods for learning mechanistic models from data. This task entails not only the accurate estimation of parameters but also a suitable model structure. Recent work on the discovery of…

Machine Learning · Computer Science 2024-07-01 Justin N. Kreikemeyer , Philipp Andelfinger , Adelinde M. Uhrmacher

In online portfolio optimization the investor makes decisions based on new, continuously incoming information on financial assets (typically their prices). In our study we consider a learning algorithm, namely the Kiefer--Wolfowitz version…

Portfolio Management · Quantitative Finance 2019-07-05 Zsolt Nika , Miklós Rásonyi

Off-policy learning refers to the problem of learning the value function of a way of behaving, or policy, while following a different policy. Gradient-based off-policy learning algorithms, such as GTD and TDC/GQ, converge even when using…

Artificial Intelligence · Computer Science 2015-12-15 Lucas Lehnert , Doina Precup

We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamical system from a sequence of noisy observations generated by the system.…

Machine Learning · Computer Science 2019-02-12 Moritz Hardt , Tengyu Ma , Benjamin Recht

Online minimization of an unknown convex function over the interval $[0,1]$ is considered under first-order stochastic bandit feedback, which returns a random realization of the gradient of the function at each query point. Without knowing…

Machine Learning · Statistics 2020-02-21 Sattar Vakili , Sudeep Salgia , Qing Zhao

This work studies constrained stochastic optimization problems where the objective and constraint functions are convex and expressed as compositions of stochastic functions. The problem arises in the context of fair classification, fair…

Machine Learning · Computer Science 2022-09-13 Srujan Teja Thomdapu , Harshvardhan , Ketan Rajawat

Real-world control systems require policies that are not only high-performing but also interpretable and robust. A promising direction toward this goal is model-based control, which learns system dynamics and cost functions from historical…

Systems and Control · Electrical Eng. & Systems 2025-11-20 Yuexin Bian , Jie Feng , Yuanyuan Shi

We consider an improper reinforcement learning setting where a learner is given $M$ base controllers for an unknown Markov decision process, and wishes to combine them optimally to produce a potentially new controller that can outperform…

Machine Learning · Computer Science 2021-07-06 Mohammadi Zaki , Avinash Mohan , Aditya Gopalan , Shie Mannor

As children grow older, they develop an intuitive understanding of the physical processes around them. They move along developmental trajectories, which have been mapped out extensively in previous empirical research. We investigate how…

Machine Learning · Computer Science 2022-09-27 Luca M. Schulze Buschoff , Eric Schulz , Marcel Binz

The paper addresses a continuous-time continuous-space chance-constrained stochastic optimal control (SOC) problem where the probability of failure to satisfy given state constraints is explicitly bounded. We leverage the notion of exit…

Systems and Control · Electrical Eng. & Systems 2025-11-26 Apurva Patil , Alfredo Duarte , Fabrizio Bisetti , Takashi Tanaka

This work proposes a method for solving linear stochastic optimal control (SOC) problems using sum of squares and semidefinite programming. Previous work had used polynomial optimization to approximate the value function, requiring a high…

Optimization and Control · Mathematics 2014-09-23 Matanya B. Horowitz , Ivan Papusha , Joel W. Burdick

This paper develops algorithms for high-dimensional stochastic control problems based on deep learning and dynamic programming. Unlike classical approximate dynamic programming approaches, we first approximate the optimal policy by means of…

Probability · Mathematics 2021-09-21 Côme Huré , Huyên Pham , Achref Bachouch , Nicolas Langrené

Many machine learning tasks can be formulated as a stochastic compositional optimization (SCO) problem such as reinforcement learning, AUC maximization, and meta-learning, where the objective function involves a nested composition…

Machine Learning · Computer Science 2023-11-23 Ming Yang , Xiyuan Wei , Tianbao Yang , Yiming Ying